Abstract: In this paper, the prediction model of coal slime flotation dosage based on GA-BP neural network is present to dispose of the problems that the prediction is not accurate in the existing coal slime flotation dosage.Firstly, the influence factors are screened out through MIV value method,and then the prediction model based on GA-BP neural network of dosing is established.MIV value method is used to simplify the network structure ,and the method of genetic algorithm is employed to optimize the neural network to improve the accuracy of the neural network model to predict the dosage.